A Comparison of the Affectiva iMotions Facial Expression Analysis Software With EMG for Identifying Facial Expressions of Emotion
[FULL TEXT READ at the publisher, open access CC BY. Author order verified at api.openalex.org: LOUISA KULKE FIRST AND CORRESPONDING, University of Gottingen; Schacht last] Kulke, L., Feyerabend, D., & Schacht, A. (2020). 'A Comparison of the Affectiva iMotions Facial Expression Analysis Software With EMG for Identifying Facial Expressions of Emotion.' Frontiers in Psychology, 11, 329. doi:10.3389/fpsyg.2020.00329. THE RESULT THAT GOES THE OTHER WAY, AND THE ARTICLE MUST PRINT IT. Sample: 20 students aged 18 to 29, mean age 21, 17 OF THE 20 FEMALE, all right-handed and none wearing glasses, with five further participants tested and excluded, and participants whose mean Affdex quality score fell below 75 per cent excluded. Task: imitate expressions from 60 frontal portraits, 20 each of happy, angry and neutral, 10 female and 10 male faces per condition, from the Karolinska Directed Emotional Faces database, 10 seconds per stimulus. Electromyography from zygomaticus major and corrugator supercilii on the left side of the face, recorded in a session separate from the video. FIGURES: r(60) = 0.761, p < 0.001 between the electromyography difference score and the Affectiva smile-minus-brow-furrow difference score, and r(60) = 0.789, p < 0.001 for the Affectiva joy-minus-anger difference score. THEIR CONCLUSION, VERBATIM: 'Happy and angry expressions were detected by both the software and by EMG above chance, while neutral expressions were more often falsely identified as negative by EMG compared to the software. Overall, EMG and software values correlated highly. In conclusion, Affectiva Affdex software can identify facial expressions and its results are comparable to EMG findings.' THIS IS A POSITIVE RESULT AND SHOULD BE REPORTED AS ONE, with its own stated limits attached: twenty people, 85 per cent female, three classes rather than seven, and deliberately imitated
[FULL TEXT READ at the publisher, open access CC BY. Author order verified at api.openalex.org: LOUISA KULKE FIRST AND CORRESPONDING, University of Gottingen; Schacht last] Kulke, L., Feyerabend, D., & Schacht, A. (2020). 'A Comparison of the Affectiva iMotions Facial Expression Analysis Software With EMG for Identifying Facial Expressions of Emotion.' Frontiers in Psychology, 11, 329. doi:10.3389/fpsyg.2020.00329. THE RESULT THAT GOES THE OTHER WAY, AND THE ARTICLE MUST PRINT IT. Sample: 20 students aged 18 to 29, mean age 21, 17 OF THE 20 FEMALE, all right-handed and none wearing glasses, with five further participants tested and excluded, and participants whose mean Affdex quality score fell below 75 per cent excluded. Task: imitate expressions from 60 frontal portraits, 20 each of happy, angry and neutral, 10 female and 10 male faces per condition, from the Karolinska Directed Emotional Faces database, 10 seconds per stimulus. Electromyography from zygomaticus major and corrugator supercilii on the left side of the face, recorded in a session separate from the video. FIGURES: r(60) = 0.761, p < 0.001 between the electromyography difference score and the Affectiva smile-minus-brow-furrow difference score, and r(60) = 0.789, p < 0.001 for the Affectiva joy-minus-anger difference score. THEIR CONCLUSION, VERBATIM: 'Happy and angry expressions were detected by both the software and by EMG above chance, while neutral expressions were more often falsely identified as negative by EMG compared to the software. Overall, EMG and software values correlated highly. In conclusion, Affectiva Affdex software can identify facial expressions and its results are comparable to EMG findings.' THIS IS A POSITIVE RESULT AND SHOULD BE REPORTED AS ONE, with its own stated limits attached: twenty people, 85 per cent female, three classes rather than seven, and deliberately imitated
Written from the fULL TEXT READ at the publisher, open access CC BY. Author order verified at api.openalex.org: LOUISA KULKE FIRST AND CORRESPONDING, University of Gottingen; Schacht last.
What our sources record
Recorded when this source was checked, figures included, with page references and quotation marks removed.
Kulke, L., Feyerabend, D., & Schacht, A. (2020). A Comparison of the Affectiva iMotions Facial Expression Analysis Software With EMG for Identifying Facial Expressions of Emotion. Frontiers in Psychology, 11, 329. doi:10.3389/fpsyg.2020.00329